_wp_scan_utf8( string $bytes, int $at, int $invalid_length, int|null $max_bytes = null, int|null $max_code_points = null, bool|null $has_noncharacters = null ): int

47function _wp_scan_utf8( string $bytes, int &$at, int &$invalid_length, ?int $max_bytes = null, ?int $max_code_points = null, ?bool &$has_noncharacters = null ): int {48	$byte_length       = strlen( $bytes );49	$end               = min( $byte_length, $at + ( $max_bytes ?? PHP_INT_MAX ) );50	$invalid_length    = 0;51	$count             = 0;52	$max_count         = $max_code_points ?? PHP_INT_MAX;53	$has_noncharacters = false;54 55	for ( $i = $at; $i < $end && $count <= $max_count; $i++ ) {56		/*57		 * Quickly skip past US-ASCII bytes, all of which are valid UTF-8.58		 *59		 * This optimization step improves the speed from 10x to 100x60		 * depending on whether the JIT has optimized the function.61		 */62		$ascii_byte_count = strspn(63			$bytes,64			"\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" .65			"\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" .66			" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f",67			$i,68			$end - $i69		);70 71		if ( $count + $ascii_byte_count >= $max_count ) {72			$at    = $i + ( $max_count - $count );73			$count = $max_count;74			return $count;75		}76 77		$count += $ascii_byte_count;78		$i     += $ascii_byte_count;79 80		if ( $i >= $end ) {81			$at = $end;82			return $count;83		}84 85		/**86		 * The above fast-track handled all single-byte UTF-8 characters. What87		 * follows MUST be a multibyte sequence otherwise there’s invalid UTF-8.88		 *89		 * Therefore everything past here is checking those multibyte sequences.90		 *91		 * It may look like there’s a need to check against the max bytes here,92		 * but since each match of a single character returns, this functions will93		 * bail already if crossing the max-bytes threshold. This function SHALL94		 * NOT return in the middle of a multi-byte character, so if a character95		 * falls on each side of the max bytes, the entire character will be scanned.96		 *97		 * Because it’s possible that there are truncated characters, the use of98		 * the null-coalescing operator with "\xC0" is a convenience for skipping99		 * length checks on every continuation bytes. This works because 0xC0 is100		 * always invalid in a UTF-8 string, meaning that if the string has been101		 * truncated, it will find 0xC0 and reject as invalid UTF-8.102		 *103		 * > [The following table] lists all of the byte sequences that are well-formed104		 * > in UTF-8. A range of byte values such as A0..BF indicates that any byte105		 * > from A0 to BF (inclusive) is well-formed in that position. Any byte value106		 * > outside of the ranges listed is ill-formed.107		 *108		 * > Table 3-7. Well-Formed UTF-8 Byte Sequences109		 *  ╭─────────────────────┬────────────┬──────────────┬─────────────┬──────────────╮110		 *  │ Code Points         │ First Byte │ Second Byte  │ Third Byte  │ Fourth Byte  │111		 *  ├─────────────────────┼────────────┼──────────────┼─────────────┼──────────────┤112		 *  │ U+0000..U+007F      │ 00..7F     │              │             │              │113		 *  │ U+0080..U+07FF      │ C2..DF     │ 80..BF       │             │              │114		 *  │ U+0800..U+0FFF      │ E0         │ A0..BF       │ 80..BF      │              │115		 *  │ U+1000..U+CFFF      │ E1..EC     │ 80..BF       │ 80..BF      │              │116		 *  │ U+D000..U+D7FF      │ ED         │ 80..9F       │ 80..BF      │              │117		 *  │ U+E000..U+FFFF      │ EE..EF     │ 80..BF       │ 80..BF      │              │118		 *  │ U+10000..U+3FFFF    │ F0         │ 90..BF       │ 80..BF      │ 80..BF       │119		 *  │ U+40000..U+FFFFF    │ F1..F3     │ 80..BF       │ 80..BF      │ 80..BF       │120		 *  │ U+100000..U+10FFFF  │ F4         │ 80..8F       │ 80..BF      │ 80..BF       │121		 *  ╰─────────────────────┴────────────┴──────────────┴─────────────┴──────────────╯122		 *123		 * @see https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-3/#G27506124		 */125 126		// Valid two-byte code points.